Abstract
SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.
Original language | English |
---|---|
Title of host publication | ECAI 2004 |
Subtitle of host publication | Proceedings of the 16th Eureopean Conference on Artificial Intelligence |
Editors | Ramon López de Mántaras, Lorenza Saitta |
Place of Publication | Amsterdam, Netherlands |
Publisher | IOS Press |
Pages | 760-764 |
Number of pages | 5 |
Volume | 110 |
ISBN (Print) | 1586034529, 978-1586034528 |
Publication status | Published - 1 Dec 2004 |
Event | 16th European Conference on Artificial Intelligence (ECAI 2004) including Prestigious Applicants of Intelligent Systems (PAIS 2004) - Valencia, Spain Duration: 22 Aug 2004 → 27 Aug 2004 |
Publication series
Name | Frontiers in Artificial Intelligence and Applications |
---|---|
Publisher | IOS Press |
Volume | 110 |
ISSN (Print) | 0922-6389 |
Conference
Conference | 16th European Conference on Artificial Intelligence (ECAI 2004) including Prestigious Applicants of Intelligent Systems (PAIS 2004) |
---|---|
Country | Spain |
City | Valencia |
Period | 22/08/04 → 27/08/04 |
Cite this
Lessons from deploying NLG technology for marine weather forecast text generation. / Sripada, Gowri Somayajulu; Reiter, Ehud Baruch; Davy, I ; Nilssen, K .
ECAI 2004: Proceedings of the 16th Eureopean Conference on Artificial Intelligence. ed. / Ramon López de Mántaras; Lorenza Saitta. Vol. 110 Amsterdam, Netherlands : IOS Press, 2004. p. 760-764 (Frontiers in Artificial Intelligence and Applications; Vol. 110).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Lessons from deploying NLG technology for marine weather forecast text generation
AU - Sripada, Gowri Somayajulu
AU - Reiter, Ehud Baruch
AU - Davy, I
AU - Nilssen, K
N1 - Including Prestigious Applicants of Intelligent Systems, PAIS 2004
PY - 2004/12/1
Y1 - 2004/12/1
N2 - SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.
AB - SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.
M3 - Conference contribution
SN - 1586034529
SN - 978-1586034528
VL - 110
T3 - Frontiers in Artificial Intelligence and Applications
SP - 760
EP - 764
BT - ECAI 2004
A2 - de Mántaras, Ramon López
A2 - Saitta, Lorenza
PB - IOS Press
CY - Amsterdam, Netherlands
ER -